Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Data Mining Practical Machine Learning Tools and Techniques

The power of feedback.

The measurement of meaning

語用論(Pragmatics)を考える

https://people.cs.pitt.edu/~litman/courses/ads/readings/douglas-cowie03.pdf

Emotional speech: towards a new generation of databases

In a speech synthesizer apparatus, a weighting coefficient training controller calculates acoustic distances in second acoustic feature parameters between one target phoneme from the same phoneme and the phoneme candidates other than the target phoneme based on first acoustic feature parameters and prosodic feature parameters, and determines weighting coefficient vectors for respective target phonemes defining degrees of contribution to the second acoustic feature parameters for respective phoneme candidates by executing a predetermined statistical analysis therefor. Then, a speech unit selector searches for a combination of phoneme candidates which correspond to a phoneme sequence of an input sentence and which minimizes a cost including a target cost representing approximate costs between a target phoneme and the phoneme candidates and a concatenation cost representing approximate costs between two phoneme candidates to be adjacently concatenated, and outputs index information on the searched out combination of phoneme candidates. Further, a speech synthesizer synthesizes a speech signal corresponding to the input phoneme sequence by sequentially reading out speech segments of speech waveform signals corresponding to the index information and concatenating the read speech segments of the speech waveform signals.

Concatenation of speech segments by use of a speech synthesizer

Concatenating units of natural speech is one method of speech synthesis. Most such systems use an inventory of xed length units, typically diphones or triphones with one instance of each type. An alternative is to use more varied, non-uniform units extracted from large speech databases containing multiple instances of each. The greater variability in such natural speech segments allows closer modeling of naturalness and di erences in speaking styles, and eliminates the need for specially-recorded, single-use databases. However, with the greater variability comes the problem of how to select between the many instances of units in the database. This paper addresses that issue and presents a general method for unit selection.

Optimising selection of units from speech databases for concatenative synthesis.

https://people.cs.pitt.edu/~litman/courses/ads/readings/iida03.pdf

A corpus-based speech synthesis system with emotion

We introduce a Multi-modal Neural Machine Translation model in which a doubly-attentive decoder naturally incorporates spatial visual features obtained using pre-trained convolutional neural networks, bridging the gap between image description and translation. Our decoder learns to attend to source-language words and parts of an image independently by means of two separate attention mechanisms as it generates words in the target language. We find that our model can efficiently exploit not just back-translated in-domain multi-modal data but also large general-domain text-only MT corpora. We also report state-of-the-art results on the Multi30k data set.

/pdf/doubly-attentive-decoder-for-multi-modal-neural-machine-3iocu1j8r6.pdf

Nick Campbell

Papers

Emotional speech: towards a new generation of databases

Concatenation of speech segments by use of a speech synthesizer

Optimising selection of units from speech databases for concatenative synthesis.

A corpus-based speech synthesis system with emotion

Doubly-Attentive Decoder for Multi-modal Neural Machine Translation